Decision Theory

CMA Inter – P12 – Management Accounting – Decision Theory
7. Decision Theory
 Decision making is the most significant aspect of the management process.
 Effective decision making is linked to fulfilment of the objectives of the
organization. An elaborately designed decision making process helps to
make a more deliberate and effective decision
 The steps of the process are discussed below
Identify the nature of decision
Gather relevant information from Internal & external Sources
on the basis of the information collected the alternatives are zeroed upon
Consider the evidences
The decision maker is ready to make his call which is decided upon in the previous
step.
Review of the decision
 The theoretical underpinnings of the decision making process is the subject matter of
Decision Theory. The following aspects are noteworthy:
(a) Decision theory involves economic and statistical approaches for studying an individual’s choices.
Because it is based on ideas, attitudes, and wishes, analysts refer to it as a theory of choice.
(b) Decision theory enables the entity to make the most rational decision feasible in unknown and
uncertain conditions, repercussions, and behaviours.
(c) In order to make better business decisions, companies worldwide use this theory to understand
how customers and markets operate.
(d) Mathematicians, economists, marketers, data and social scientists, biologists, psychologists,
philosophers, and politicians use two theory forms: normative and descriptive.
Decision making in Certainty
 In cases when only one state of nature is to be considered because of the nature of the problem or
because of lack of information are called decision-making under certainty.
 If the decision maker is certain as regards to the probability of happening/ not happening of an
outcome, he is said to operate under condition of certainty.
 Thus it may be stated that in the realm of decision making, under condition of certainty each action
will lead invariably to a specific outcome.
 In this situation only one state of nature exits and its probability is one.
 In simple words, the decision-maker is conformed to what will happen when a decision is being made.
CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.1
 It is a condition where the future is cent percent definite.
 This situation is conformed because of the availability of all reliable information.
 Thus the cause and effect are known with certainty. Due to known conditions, there are no conflicts in
decision-making.
 This condition exists in routine decisions such as day-to-day activities, payment of wages, salaries,
 Decision Matrix:
▪ The standard format for the evaluation of alternatives in decision theory is that of a decision
matrix. In a decision matrix, the alternatives open to the decision-maker are tabulated against the
possible states of nature.
▪ The alternatives (acts) are represented by the rows of the matrix, and the states of nature by
the columns.
▪ The decision matrix is also referred as the payoff matrix when the cell values are presented in
terms of net benefit.
▪ For the purpose of understanding a payoff table, or decision matrix, is shown below.
▪ The decision will be made among m of alternatives, identified as A1, A2, A3……… Am There may be
more than one future “state of nature” N.
▪ The model considered here allows for n different futures. These future states of nature may not be
equally likely, but each state will have some (known or unknown) probability of occurrence
▪ Since the future must take on one of the n values of the sum of the n values of must be 1.0.
▪ The outcome (or payoff, or benefit gained) will depend on both the alternative chosen and the
future state of nature that occurs.
▪ For example, if the alternative Ai is chosen and state of nature Nj takes place (as it will with
probability pj), the payoff will be outcome Oij A full payoff table will contain m times n possible
outcomes.
Table: Decision Matrix

States of Nature/Probability
N1 N2 ----- Nj ----- Nn
Alternative P1 P2 ----- Pj ----- Pn
A1 O11 O12 ----- O1j ----- O1n
A2 O21 O22 ----- O2j ----- O2n
Ai Oil Oi2 ----- Oij ----- Oin
Am Oml Om2 ----- Omj ----- Omn

▪ Under condition of certainty there would be only one state of nature as the future is known with
certainty. Thus the decision matrix or payoff matrix would be as given below.
Pay off Matrix (under condition of certainty)

Alternative State of nature (pj = 1)
A1 O1
A2 O1
A3 O1
A4 O1
Am Om
Decision making Under Risk

 Risk refers to a condition where there is a possibility of an adverse deviation from a desired outcome’.
 In a risky environment, the decision maker operates under condition of imperfect information.
 A manager may understand the problem and the alternatives, but has no guarantee how each solution
will work. This is a fairly common condition under which the decision maker operates.
 When a manager lacks perfect information risk arises.
 Under a state of risk, the decision maker has incomplete information about available alternatives but
has a good idea of the probability of outcomes for each alternative.
Probabilities
 Probabilities are mathematical expression which is used to denote the likelihood that an event or
state of nature will occur.
 It is expressed in decimal and varies between 0 and 1.
 When the probability of occurrence of an event is 0, it denotes nil likelihood of occurrence whereas
a value of 1 signifies absolute certainty – a definite occurrence.
 The total of the probabilities for events that can possibly occur must sum to 1.0
Subjective & Objective Probabilities
 According to objective interpretations, probabilities are real. We may discover them by logic or
estimate them through statistical analyses.
 According to subjective interpretations, probabilities are human beliefs’.
 Probabilities (objective) may be obtained in two manners:
(a) A priori probabilities are derived from inherent symmetries, as in the throw of a die.
(b) Statistical probabilities are obtained through analysis of homogenous data
 In business decisions, the probabilities (chances of a particular state of nature of happening/not
happening) are often estimated based on managerial judgement (subjective probabilities)
Aspects of Probabilities
 The probability values assigned to each of the possible outcomes must be between 0 and 1; and
 The probable values assigned to all of the possible outcomes must total 1.
Probability in Different Events
Independent Events
 If the occurrence or non-occurrence of one event does not change the probability of the occurrence
of the other event, the two events are said to be independent.
 The addition law can be used when there are two possible events and we want to know the
probability that at least one of the events will occur. In other words, for events A and B, we want
to know the probability that event A or event B or both events will occur.
 Events that are independent and not mutually exclusive can have sample points in common. That is,
in some cases both A and B can occur. We need to include those cases in our calculation of the
probability that at least one of the events will occur; but we do not want to double count them
because of counting them once with A’s probability and again with B’s probability.
 The union of events A and B is the event containing all the sample points belonging to A or B or

both. It represents the probability that either A or B will occur, including the probability that both
will occur.
 Calculating the Joint Probability of two Independent Events
The area of the overlap—the joint probability—is the probability that both events will occur. That
area qualifies to be included in the probability that either one of the events will occur, because one
of the events certainly occurs in the area of the overlap. But we want to include it once, not
twice, so we subtract it from the sum of the two events’ probabilities.
Mutually Exclusive Events
 If events are mutually exclusive, it means that if one of them occurs, the other event cannot
occur. Either one or the other can occur but not both.
Dependent Events and Conditional Probability
 When there are two events, A and B, and the occurrence of B depends upon the occurrence of A,
the probability that both events will occur is the probability that the first event will occur,
multiplied by the conditional probability that the second event will occur given that the first event
has already occurred.
Methods Of Assigning Probable Values
Classical This method assumes that each possible outcome has an equal probability of
Method occurring. Thus, if there are ten possible outcomes, each outcome is assumed to
have a 10% probability of occurring. This is the method used to assign
probabilities to coin tosses or dice rolls. Business decisions don’t usually involve
coin tosses or dice rolls, so the classical method is seldom used in situations of
business uncertainty.
Relative When factual information is available that can be used to determine the
Frequency probability of something occurring; the use of that information to assign
or Objective probabilities is called the relative frequency method. The information may come
Method from a sample, analytical data, or any other reliable source.
Subjective With the subjective method of assigning probabilities, we use whatever data is
Method available and add to that data our own experience and intuition. After
considering all available information, we assign a probable value that expresses
our degree of belief that the outcome will occur. Subjective probability is
personally determined, and different people will assign different probabilities to
the same event. Despite this relative freedom in assigning probabilities, the two
necessary requirements for all probabilities must nevertheless be met:
 The probable value for each possible outcome must be between 0 and 1;
 All the probabilities for all the possible outcomes must total 1.
Expected Value / Mean /Average Value (or Expected Return)

 The expected value of an action is found by multiplying the probability of each potential outcome
by its payoff. Therefore, expected value, or expected return, is a weighted average of the possible
returns, with the weights being the probabilities of occurrence.
 The weights are the probabilities for each of the values.
 It is not possible to calculate a weighted average for a continuous probability distribution because
the number of possible variables is infinite.
 The general model of decision making under risk when probabilities may be assigned in an objective
manner to the states of nature is through the Expected Value criterion.
Investment Appraisal and Risk
 Risk for an investment can be measured by the variability, or dispersion, of its potential returns
around the mean return. The mean return is given by the expected value of the returns. The
variance and the standard deviation of a set of potential returns are measurements of their
dispersion about the mean. Thus, the risk of an investment is measured by the variance and
standard deviation of its potential returns.
Standard Deviation and Variance as a Measure of Risk
 The variance and the standard deviation measure how far from the mean (the expected value) the
various possible values lie.
 The variance is used to summarize the variability (Dispersion) in the values of a random variable.
The amount of variability in the values of the random variable around their mean (or average) is
the amount by which they are dispersed, or the amount of their dispersion.
 The greater the dispersion of the values around their mean, the greater the risk associated with
the values because there is a larger chance that the actual results will be different from the
expected value.
 The standard deviation of the probability distribution of these subjectively determined potential cash
flows expresses the dispersion, or variability, of possible returns around the expected return. If the
standard deviation is large, it means the variability of returns is large and the risk of the project is
higher. Thus, standard deviation is a measure of risk.
 The variance and standard deviation of each of the expected cash flows is calculated in the same
way as the variance and standard deviation. The narrower the distribution of the data, the lower
the standard deviation will be. The lower the standard deviation, the lower the risk. The wider the
distribution of data, the higher the standard deviation and the higher the risk.
 Again coefficient variation also measures the risk. Coefficient of variation is the relative measure of
dispersion. It measures the standard deviation relative to the mean in percentages
Expected Value in Estimating Future Cash Flows
 Expected value is a term that means a weighted average of the possible values using the
probabilities as the weights.
 Estimating, or projecting, future cash flows are an important application of expected value. It is
used in capital budgeting analysis for evaluating potential projects.
 A budgeted amount of future cash flow is often thought of as an absolute number. Unfortunately,
though, future cash flows cannot be accurately ascertained because there are many events that can
affect a project’s net cash flows. Every project has numerous possible future cash flows. A project
has a range of estimated cash flows that reflect different possibilities that management can foresee.
 In determining the various possible cash flows, management must:
(a) To determine which factors have affected the net cash flows of similar projects in the past,

(b) To make assumptions about each of those events and the manner in which those events might
affect the current project.
(c) Once these specific assumptions have been formulated, the management accountant then estimates
the impact that each assumption could have on the net cash flow in each year of the project’s
life. This will be a discrete probability distribution (not a continuous one), and the probabilities
for each year will all sum to 1 or 100%.
(d) The management accountant will then calculate the expected value
(e) These calculated expected values of future cash flows will be the cash flows used in the capital
budgeting analysis for each year.
Decision Models
 Step I. To determine all possible alternatives
 Step II. To identify the future scenario
 Step III. To prepare a pay-off table
 Step IV. Selecting the best alternative
Decision Making with Probabilities
 In essence, the EV represents a weighted average of the outcomes, using probabilities as weights.
The alternative selected is the one with the highest EV for maximization problems and the lowest
EV for minimization problems
Limitations of the Expected Value Model:
 Not all future events are foreseeable and, therefore, may be omitted from the model
 Future events can be overlap between future events.
 It is difficult to accurately assess the probability of future events.
 The model ignores qualitative considerations in making a decision.
 The model ignores the decision maker’s attitude towards risk.
Expected Value of Perfect Information (EVPI)
 Perfect information is knowledge about the future that would enable us to make the best choice
today for any possible situation in the future. If we knew in advance the future state of the
economy, we could make a much more informed choice between say, Project X and Project Y.
 As we calculate the expected value of this perfect information, keep in mind that we do not know
in advance what the perfect information will be. In other words, we must determine what it would
be worth to us to know this perfect information before we know what we are buying.
 Companies can sometimes obtain information that reduces or eliminates the uncertainty associated
with the different future events/states of nature of a problem. The EVPI refers to the maximum
amount a company would pay to obtain this information
 Limitations of EVPI
Perfect information is rarely, if ever, available. When determining whether to obtain additional
information, the decision maker must weigh the additional expected value arising from perfect
information against the costs of obtaining this information.
Decision making Under Uncertainity

 Uncertainty, in common parlance, is a state of not knowing whether a proposition is true or false.
 In the absence of homogenous data, neither priori probabilities nor statistical inferences can be used
to define an opinion about a data set.
 ‘Measureable uncertainty’ to describe opinions based on probabilities.
 ‘Unmeasurable uncertainty’ to describe opinions based on human judgements.
 In simple terms, situations where objectives probabilities cannot be assigned to the states of the
nature as no prior information is available gives rise to the condition of decision making under
uncertainty.
 An individual is uncertain of a proposition if she
 does not know it to be true or false or
 is oblivious to the proposition.
 Probability is often used as a metric of uncertainty, but its usefulness is limited. At best,
probability quantifies perceived uncertainty.
 A decision problem, where a decision-maker is aware of various possible states of nature but has
insufficient information to assign any probabilities of occurrence to them, is termed as decision-
making under uncertainty. A decision under uncertainty is when there are many unknowns and no
possibility of knowing what could occur in the future to alter the outcome of a decision.
 Decision making under uncertainty, as under risk, involves alternative actions whose payoffs depend
on the states of nature. Specifically, the payoff matrix of a decision problem with m alternative
actions and n states of nature can be represented by a m × n matrix, as follows;
s1 s2 s3 sn
a1 p (a1, s1) p (a1, s2) p (a1, s3) p (a1, sn)
a2 p (a2, s1) p (a2, s2) p (a2, s3) p (a2, sn)
a3 p (a3, s1) p (a3, s2) p (a3, s3) p (a3, sn)
.
.
.
am p (am, s1) p (am, s2) p (am, s3) p (am, sn)
 The element ai represents action i and the element sj represents state of nature j. The payoff or
outcome associated with action ai and state sj is p(ai, sj). In decision making under uncertainty, the
probability distribution associated with the states sj, j = 1, 2, c, n, is unknown as it cannot be
determined.
 This absence of information has led to the development of some special decision criteria which may
be categorised as
The The maximin (minimax) criterion is based on the conservative attitude of making
Minimax the best of the worst-possible conditions). The decision maker would zero upon
(Maximin) such a decision which will give him optimum results under the given condition.
Criterion
If p(ai, sj) is loss or cost , then selection of an action is made on the basis of
minimax criterion as the objective would be to minimise loss or cost (as the
payoff denotes loss or cost)
On the contrary, If p(ai, sj) is profit or revenue , then selection of an action is
made on the basis of maximin criterion as the objective would be to maximise
profit or revenue (as the payoff denotes profit or revenue)
The Laplace This is based on the principle of insufficient reason. The simple argument is that

Criterion because the probability distributions are not known, there is no reason to believe
that the probabilities associated with the states of nature are different. The
alternatives are thus evaluated on the basis of the assumption that all states of
nature are equally likely to occur. Given that the payoff p(ai, sj) represents gain,
the best alternative is the one that yields the maximum expected value (using
equal probability). And in situation payoff p(ai, sj) represents loss the minimum
value represents the best alternative.
The Savage Under this rule, the degree of conservatism in the minimax (maximin) is
Criterion moderated by replacing the (gain or loss) payoff matrix p(ai, sj) with a loss (or
regret) matrix, r(ai, sj). Since the payoff matrix represents cost, Minimax
criterion is to be applied on the basis of the conservative principle. Thus
maximum values of each row is considered and the minimum of them is considered
and the action representing the minimax value is the best decision.
The Hurwicz The Hurwicz criterion, is designed to represent different decision-making
Criterion attitudes, ranging from the most liberal (optimistic) to the most conservative
(pessimistic). This is also referred as condition of equal likelihood.
One parameter α is used as the index of optimism. If α = 0, then the criterion
reduces to conservative minimax criterion, on the basis of the best of the worst
conditions. If α = 1, then the criterion is generous because it is based on the
underlying assumption of the best of the best conditions. The degree of optimism
(or pessimism) can be adjusted by selecting a value of a between 0 and 1. In the
absence of strong feeling regarding extreme optimism and extreme pessimism, α =
0.5 which indicates a fair choice, neither
Decision Tree
 It is essentially a visual graph that uses the branching method to map every possible outcome of a
particular decision.
 The various alternatives, based upon possible future environmental conditions, and the payoffs
associated with each of the decisions branch from the trunk.
 Decision tree shows a complete picture of a potential decision and allows a manager to graph
alternative decision paths.
 Generally, decision trees are used to evaluate decisions under conditions of risk
 The decision tree is a flexible method.
 It can be used for many situations in which emphasis can be placed on sequential decisions, the
probability of various conditions, or the highlighting of alternatives.
 Decision tree is a pictorial method of showing a sequence of interrelated decisions and their expected
outcomes. Decision trees can incorporate both the probabilities of, and values of, expected
outcomes, and are used in decision-making
 Merits of Decision Trees
(a) All the possible choices that can be made are shown as branches on the tree.
(b) All the possible outcomes of each choice are shown as subsidiary branches on the tree.
Theory Questions:
1. Multiple Choice Question
Q1 A type of decision-making environment is
(a) Certainty (b)Uncertainty (c)Risk (d) All of these
Q2 Which of the following criterion is not used for decision-making under uncertainty?
(a) Maximin (b)Maximax (c)Minimax (d)Minimize expected loss
Q3 Decision theory is concerned with
(a) Methods of arriving at an optimal decision
(b) Selecting optimal decision in a sequential manner
(c) Analysis of information that is available
(d) All of these
Q4 Which of the following criterion is not applicable to decision-making under risk?
(a) Maximize expected return (b) Maximize return
(c) Minimize expect regret
(d) Knowledge of likelihood occurrence of each state of nature
Q5 The minimum expected opportunity loss (EOL) is
(a) Equal to EVPI (b)Minimum regret (c)Equal to EMV (d)Both (A) and (B)
Q6 The expected value of perfect information (EVPI) is
(a) Equal to expected regret of the optimal decision under risk
(b) The utility of additional information (c) Maximum expected opportunity loss
(d) None of the above
Q7 The value of the coefficient of optimism (a) is needed while using the criterion of
(a) Equally likely (b)Maximin (c)Realism (d)Minimax
Q8 The decision-maker’s knowledge and experience may influence the decision-making process wi.en
using the criterion of
(a) Maximax (b)Maximax regret (c)Realism (d)Maximin
Q9 The difference between the expected profit under conditions of risk and the expected profit with perfect
information is called
(a)The expected value of perfect information (b)Expected marginal loss
(c) None of the above (d)Any one of the above
Q10 A situation in which a decision maker knows all of the possible outcomes of a decision and also knows the
probability associated with each outcome is referred to as
(a) Certainty. (b)Risk. (c)Uncertainty. (d)Strategy
Q11 Which of the following methods of selecting a strategy is consistent with risk averting behaviour?
(a) If two strategies have the same expected profit, select the one with the smaller standard deviation.
(b) If two strategies have the same standard deviation, select the one with the smaller expected profit.
(c) Select the strategy with the larger coefficient of variation. (d) All are correct
Q12 Which one of the following does not measure risk?
(a) Coefficient of variation (b)Standard deviation
(c) LPP (d)All of the above are measures of risk.
Q13 A situation in which a decision maker must choose between strategies that have more than one possible
outcome when the probability of each outcome is unknown is referred to as
(a) Diversification. (b) Certainty. (c) Risk. (d) Uncertainty.
Q14 If a decision maker is risk averse, then the best strategy to select is the one that yields the
(a) Highest expected payoff. (b)Lowest coefficient of variation.
(c) Highest expected utility. (d)Lowest standard deviation
Q15 Circumstances that influence the profitability of a decision are referred to as
(a) Strategies. (b)A payoff matrix. (c)States of nature.
(d) the marginal utility of money
Q16 A strategy that yields an expected monetary payoff of zero is called a
(a) Risk-neutral strategy. (b)Fair game. (c)Zero-sum game. (d)Certainty equivalent
Q17 A matrix that, for each state of nature and strategy, shows the difference between a strategy’s payoff and
the best strategy’s payoff is called
(a) A maximin matrix. (b)A minimax regret matrix.
(c) A payoff matrix. (d)An expected utility matrix
Q18 The sequence of possible managerial decisions and their expected outcome under each set of
circumstances can be represented and analysed by using
(a) The minimax regret criterion. (b)A decision tree.
(c) A payoff matrix. (d)Simulation
Q19 The expected value of perfect information is calculated by subtracting:
(a) The minimum expected opportunity loss from the expected opportunity loss with perfect information.
(b) The maximum EMV from the minimum expected opportunity loss.
(c) EVSI from the expected return with perfect information.
(d) The maximum EMV from the expected return with perfect information.
Q20 The maximin criterion is a feature of which of the following?
(a) Deterministic model (b)Decision-making under uncertainty
(c) Optimization (d)Decision-making under certainty
Answers:
1 D 2 D 3 D 4 B 5 D 6 A 7 C 8 C 9 A 10 B
11 A 12 C 13 D 14 C 15 C 16 B 17 B 18 B 19 A 20 b
2. True or False:
Q1 Decision theory provides a method for rational decision making when the consequences are not True
fully known
Q2 Companies benefit most from considering their risks when they are performing well and when True
markets are growing in order to sustain growth and profitability
Q3 A decision maker is risk neutral if he is concerned with what will be the most likely outcome True
Q4 The decision outcome resulting from the same information may vary from manager to manager True
as a result of their individual attitude to risk
Q5 “Risk” can be defined in many ways. One definition has a negative connotation: “a condition in True
which there is a possibility of an adverse deviation from a desired outcome.”
Q6 The variance and standard deviation both give an idea of the variability of the possible values True
about the mean.
Q7 Standard deviation is always expressed in the same units as the distribution True
Q8 Uncertainty is risk that can be measured False
Q9 If the occurrence or non-occurrence of one event does not change the probability of the True
occurrence of the other event, the two events are said to be independent.
Q10 The expected value of an action is found by multiplying the probability of each potential True
outcome by its payoff.
3. Fill in the Blanks
Q1 …………………………is a term that means a weighted average of the possible values using the probabilities as the
weights.
Q2 A_________amount of future cash flow is often thought of as an absolute number.
Q3 Approaches have been developed to choose the best option when the decision maker has several ……….and
there is uncertainty with respect to future events.
Q4 If a decision maker can estimate the________of the future events, these should be incorporated into the
decision model.
Q5 _________is knowledge about the future that would enable us to make the best choice today
for any possible situation in the future.
Q6 ………………………….is the systematic process of gathering, analysing and reporting data about markets to
investigate, describe measure, understand or explain a situation or problem facing a company or
organisation.
Q7 _________can be either primary (collected at first hand from a sample of respondents),
or secondary (collected from previous surveys, other published facts and opinions, or from experts).
Q8 ________data tells us why consumers think/buy or act the way they do.
Q9 ……………………………………tables identify and record all possible outcomes (or pay-offs) in situations where the
action taken affects the outcomes.
Q10 The______ decision rule suggests that a decision maker should select the alternative that offers the least
unattractive worst outcome.
Answers
1 Expected value 2 Budgeted 3 Alternatives
4 Probabilities 5 Perfect information 6 Market research
7 Data 8 Qualitative 9 Pay-off
10 Maximin
4. Essay Type Questions:

Q1 What is Decision Theory and how is it related to other Theories?
Q2 What are the most important methods to quantify risk?
Q3 Outline important characteristics of the risk evaluation process
Q4 Discuss the goal in the decision-making process.
Q5 What do you mean by uncertainty in decision making?
Q6 Explain why it can be helpful to involve others when making decisions involving uncertainty.
Q7 What is a Decision Tree and what are its applications?
Q8 What do you mean by Expected Value and Perfect Information?
Q9 What are the examples of risk and uncertainty?
Q10 Which are the risks faced by a company?
Q11 What are the determinants of the risks that a company faces?
Q12 What do you mean by Expected Value?
Q13 What is Uncertainty and Risk?
Q14 How a Decision Tree is constructed?
Q15 Briefly explain the concepts ‘Perfect Information’ and ‘Value of Perfect Information.’?
Q16 What is risk in decision making?
Q17 What is the Difference between Risk and Uncertainty?
Practical Questions & Case Studies

Que 1 (SM Solved case 1 – 538)
Mr Pratap is considering setting up his stall in the playground in the evening of a particular day, say 20th
August 2022. He has the option of selling ice creams or coffee. He has the option of buying Ice creams from a
whole seller @ Rs.56 each and selling them for @ Rs.60 each. Thus he would make a profit of Rs.4 on each Ice
cream cone. On a sunny day he sales 200 cones, but if it is a rainy day then sales fall and thus he is able to sell
only 80 cones. On the contrary, he can sell coffee whereby he can make a profit of Rs.6 per cup. On a sunny
day he sales 100 cones, but if it is a rainy day then sales increases and thus he is able to sell 160 cups.
Represent this in a payoff matrix

In its sales forecasting, an appliance retailer develops a set of probabilities for sales in each of its product lines
for the coming year. Sales forecasts for two of these product lines are as follows:
▪ Refrigerators: There is a 30% probability that sales of refrigerators will be ₹50,00,000; a 50% probability
that sales will be ₹75,00,000; and a 20% probability that sales will be ₹1,00,00,000.
▪ Electric Ranges: There is a 25% probability that sales of electric ranges will be ₹20,00,000; a 55%
probability that sales will be ₹30,00,000; and a 20% probability that sales will be ₹ 50,00,000.
The forecasts for these appliances relate to sales for the following year. Therefore, the actual events (sales of
refrigerators and ranges) will both be occurring at the same time. The forecast for sales of refrigerators is not
dependent on sales of electric ranges occurring, and the forecast for sales of electric ranges is not dependent on
sales of refrigerators occurring. Thus sales of refrigerators and sales of ranges are independent of each other.
What is the probability that sales of refrigerators will be ₹75,00,000 or sales of electric ranges will be
₹30,00,000 next years?

Subbuji is a small vendor who is undecided on what to sell in the fairground as a fair is to be organized in ten
days. He has the option of selling tea or ice creams on a day one (16th August 2022) of the fair. He has made a
projection that selling tea would fetch him a profit of ₹300 if it rains on 16th August 2022, but if it is sunny and
humid on the day, he would not have much customers and then he would make a profit of ₹30. If he sells ice
cream his profit is much higher (₹150) if 16th August 2022 is hot and humid, but if he decides to sell ice cream
and it rains on that day then his profit would be ₹10.
How would he make the decision of what to sell (tea or ice cream) on 16th August 2022?
Que 4 (Illustartion 1 – 547)

We are comparing two investment projects. Both have expected returns of 20%, but the standard deviation of
Project A’s returns is 15%, while the standard deviation of Project B’s returns is 9%. Which one is relatively
riskier?

Two investments have different expected returns. Project A’s expected return is 20% and the standard

deviation of its returns is 15%. Project B’s expected return is only 10%, while the standard deviation of its returns
remains at 9%. Which project is relatively riskier?

You are required to select from the following two Projects, which are mutually exclusive:
Estimated Net Cash Flows (₹) Probability
Project X:
2,000 0.3
3,000 0.4
4,000 0.3
Project Y:
1,000 0.2
2,000 0.2
3,000 0.2
4,000 0.2
5,000 0.2
The Expected value of both the Projects = ₹3,000

Building Ltd. owns land in Noida and intends to build a condominium development on the site. The company
is deciding on whether to build a small, medium or large development. Demand is uncertain and fluctuates;
demand could be low, medium or high. Management at Building Ltd. has determined profit payoffs will be:
Demand(all amounts in ₹ 000s)
Alternatives Low Medium High
Small D1 1,400 1,400 1,400
Medium D2 1,100 1,600 1,600
Large D3 (1,300) 1,200 2,100
Management has determined the probabilities of demand to be:
Probabilities:
Low = P (low) = 0.20
Medium = P (medium) = 0.35
High = P (high) = 0.45
What is the expected value of each alternative.

The following information is available for a Company:

Sales Volume (units) Probability (%)
10,000 10
12,000 15
14,000 25
16,000 30
18,000 20
Projected sales and costs are as under:
Sales Price per unit: ₹ 6; Variable Cost per unit: ₹ 3.50; Fixed Costs: ₹ 34,000
Required:
1 Probability that the Company will at least Break-even
2 Probability that the Profit will be at least ₹ 10,000.

In Que 7, the best alternative was to build a medium condominium complex as this resulted in the highest
expected value (EV = ₹1,500). If perfect information were available, that is, the probabilities were known with
certainty, the optimal decision strategy is:
▪ If low demand occurs, build a small complex.
▪ If medium demand occurs, build a medium complex. If high demand occurs, build a large complex.
Find out EVPI.

ABC Company Co is trying to set the sales price for one of its products. Three prices are under consideration,
and expected sales volumes and costs are as follows.
Price per unit ₹4 ₹4.30 ₹4.40
Expected sales volume (units)
Best possible 16,000 14,000 12,500
Most likely 14,000 12,500 12,000
Worst possible 10,000 8,000 6,000
Fixed costs are ₹ 20,000 and variable costs of sales are ₹ 2 per unit. Which price should be chosen?

Given the following Payoff table of profits generated by an entity under differing condition of the future state

of nature.
States of Nature
Alternatives S1 S2 S3 S4
A1 3 5 8 -1
A2 6 5 2 0
A3 0 5 6 4
State which can be chosen as the best act using:
1 Maximax,
2 Maximin,
3 Minimax regret (Savage criterion),
4 Equal likelihood (Laplace criterion),
5 Hurwicz Alpha criterion α=0.4
6
Julien Point School (JPS) is preparing a summer camp in the jungles of Bagora, District of Darjeeling to train
individuals in wilderness survival. JPS estimates that attendance can fall into one of four categories: 200, 250,
300, and 350 persons. The cost of the camp will be the smallest when its size meets the demand exactly.
Deviations above or below the ideal demand levels incur additional costs resulting from constructing more
capacity than needed or losing income opportunities when the demand is not met. Letting a1 to a4 represent
the sizes of the camp (200, 250, 300, and 350 persons) and s1 to s4 the level of attendance, the following table
summarizes the cost matrix (in thousands of Rupees) for the situation:
S1 S2 S3 S4
a1 5 10 18 25
a2 8 7 12 23
a3 21 18 12 21
a4 30 22 19 15
State the best alternative using: (i) Minimax, (ii) Laplace, (iii) Savage Criterion (Minimax Regret), (iv) Hurwicz
Criterion.

A company can choose to launch a new product XYZ or not. If the product is launched, expected sales and
expected unit costs might be as follows:
Units Sales Probability ₹ Unit costs Probability
10,000 0.8 6 0.7
15,000 0.2 8 0.3
What are the several outcomes

LT Ltd. owns land in Bangalore and intends to build a project development on the site. The company is

deciding on whether to build a small, medium or large development. Demand is uncertain and fluctuates;
demand could be low, medium or high. Management at LT Ltd. has determined profit payoffs will be:
Demand (all amounts in ₹ 000s)
Alternatives Low Medium High
Small d1 1,400 1,400 1,400
Medium d2 1,100 1,600 1,600
Large d3 (1,300) 1,200 2,100
Management has determined the probabilities of demand to be:
Low = P (low) = 0.20
Medium = P (medium) = 0.35
High = P (high) = 0.45
Apply decision Tree Approach

B Ltd. has a new wonder product, the V, of which it expects great things. At the moment the company has two
courses of action open to it, to test market the product or abandon it.
▪ If the company test markets it, the cost will be ₹ 1,00,000 and the market response could be positive or
negative with probabilities of 0.60 and 0.40.
▪ If the response is positive the company could either abandon the product or market it full scale.
▪ If it markets the V in full scale, the outcome might be low, medium or high demand, and the respective
net gains/ (losses) would be (200), 200 or 1,000 in units of ₹1,000 (the result could range from a net loss of
₹ 2,00,000 to a gain of ₹10,00,000). These outcomes have probabilities of 0.20, 0.50 and 0.30
respectively.
▪ If the result of the test marketing is negative and the company goes ahead and markets the product,
estimated losses would be ₹ 6,00,000.
▪ If, at any point, the company abandons the product, there would be a net gain of ₹ 50,000 from the sale
of scrap. All the financial values have been discounted to the present.
Required
1 Draw a decision tree.
2 Include figures for cost, loss or profit on the appropriate branches of the tree.

TT Newsagents stocks a weekly health magazine. The owner buys the magazines for ₹ 0.30 each and sells

them at the retail price of ₹0.50 each.
At the end of the week unsold magazines are obsolete and have no value. The estimated probability
distribution for weekly demand is shown below.
Weekly demand in units Probability
20 0.20
30 0.55
40 0.25
Total 1.00
You are required to calculate the following:
1 What is the expected value of demand?
2 If the owner is to order a fixed quantity of magazines per week how many should that be?
3 Assume no seasonal variations in demand.

The Profit Budget of ABC Company is given below:
Profit Budget for year ending 31st March 2022
Particulars ₹
Sales (1,00,000 units @ ₹10) 10,00,000
Variable costs:
Manufacturing (₹ 5 per unit) 5,00,000
Marketing (₹0.50 per unit) 50,000 5,50,000
Contribution: 4,50,000
Fixed costs:
Manufacturing 2,00,000
Marketing 50,000
Administrative 1,00,000 3,50,000
Profit Before Tax 1,00,000
Tax (assumed at 50%) 50,000
Profit after Tax 50,000
Note: Manufacturing variable cost is:
▪ ₹ 5.10 per unit at volume of 80,000 units
▪ ₹ 5.00 per unit at volume of 1,00,000 units
▪ ₹ 4.80 per unit at volume of 1,10,000 units
The marketing manager has given the sales forecast as follows.
▪ Probability 0.3 - 80,000 units
▪ Probability 0.5 - 1,00,000 units
▪ Probability 0.2 - 1,10,000 units
The production manager has indicated the variable manufacturing cost to be as follows:
▪ Probability 0.2 - ₹ 5.10 per unit
▪ Probability 0.6 - ₹ 5.00 per units
▪ Probability 0.2 - ₹ 4.80 per units
The Management Accountant is to work out the profit Budget taking the above factors into account. All other
costs are as given earlier. Prepare a Probabilistic Budget.

When forecasting cash flows for investment projects, we might make several sets of forecasts for each project to

reflect the various alternative states of the economy that might ensue. If we are comparing two project
proposals, both for one-year projects, we might make several forecasts for the cash flows, as follows:
Project X (₹) Project Y (₹)
Economy in a deep recession 2,00,000 1,00,000
Economy in a mild recession 2,50,000 2,00,000
Economy stable 3,00,000 3,00,000
Economy in a minor expansion 3,50,000 4,00,000
Suppose economists forecast that the probability of a deep recession occurring next year is 5%, a mild recession
is 10%, a stable economy is 50%, a minor expansion is 25%, and a major expansion is 10%. Using these
projections, calculate the expected value of the cash flows for both projects.

A manager is considering whether to make product X or product Y, but only one can be produced. The
estimated sales demand for each product is uncertain. A detailed investigation of the possible sales demand
for each product gives the following probability distribution of the profits for each product
Product X probability distribution
Outcome Estimated Probability Weighted Profit (₹)
Profits of ₹6,00,000 0.10 60,000
Profits of ₹7,00,000 0.20 1,40,000
Profits of ₹8,00,000 0.40 3,20,000
Profits of ₹9,00,000 0.20 1,80,000
Profits of ₹10,00,000 0.10 1,00,000
Expected value 8,00,000
Product Y probability distribution
Outcome Estimated probability Weighted Profit (₹)
Profits of ₹ 4,00,000 0.05 20,000

Profits of ₹ 6,00,000 0.10 60,000
Profits of ₹ 8,00,000 0.40 3,20,000
Profits of ₹ 10,00,000 0.25 2,50,000
Profits of ₹12,00,000 0.20 2,40,000
Expected value 8,90,000
Que 20 (SM EX Q 1 – 583)

ABC Corporation is introducing a new product and must decide on a selling price. The variable cost per

unit is ₹5.60. Senior management has narrowed the pricing alternatives to two choices: ₹14.50 or ₹ 8.20 per
unit. Management estimates sales levels and the probability of attaining these levels as:
Selling price of ₹ 8.20:

Units Probability
15,000 5%
10,000 85%
8,000 10%
Selling price of ₹ 14.50:
Units Probability
4,700 5%
3,800 65%
2,600 30%
As the volume levels noted above are in the relevant range, fixed costs remain constant regardless of the
selling price chosen.
Required:
1 Using a payoff table, calculate the optimal price ABC Corporation should charge.
2 Restate Part 1 using a decision tree
Que 21 (SM EX Q 2 – 584)

A dealer of perishable product earns a Profit of ₹3 per kg, if he can sell within two days, but incurs a loss of ₹2
per kg, if fails to do so. The estimated demand for the product and the relative probabilities are as given
below:
Estimated Demand Probability
0 kg 5%
1 kg 20%
2 Kg 40%
3 kg 25%
4 kg 10%
In order to maximize his profit, what should be the quantity of stock that he should hold?
Que 22 (SM EX Q 3 – 584)

XYZ Co. is considering rearranging its plant to increase efficiency. If the rearrangement is completely successful,

anticipated operating costs will be ₹ 200,000 per annum. If the rearrangement is partially successful,
anticipated operating costs are expected to be ₹ 310,000. If unsuccessful, operating costs are anticipated to be
₹ 510,000. The probability of complete success is 50%, partial success 30% and failure 20%. If the company
does not rearrange, operating costs will be ₹ 400,000.
Required
1 Prepare a payoff table (alternatives are rearrange or do not rearrange).
2 Restate requirement 1 in a decision tree format.
3 XYZ has an opportunity to hire a consultant who could predict the success rate with certainty. How
much should XYZ Co. be willing to pay for such a report?
Que 23 (SM EX Q 4 – 584)

You own the rights to sell Rolls at the local park. The weather network predicts the probability of rain at 60%
for the game coming up tomorrow. You have to decide today whether you will set up Roll stand inside or
outside. If you set up outside and it does not rain, you expect to sell 800 hot dogs, but if it rains you will only
sell 200 Rolls. If you set up inside and it does not rain, you will sell 300 hot dogs, but, if it rains, you will sell 700
Rolls. Each Roll generates a contribution margin of ₹2.
Required
1 Where should you set up, inside or outside?
2 What is the most you would pay someone to predict (with 100% accuracy) tomorrow’s weather?
3 At what rain probability would you be indifferent between setting up inside or outside?
Que 24 (SM EX Q5 – 585)

Bajaj Company is considering three alternative machines to produce a new product. The cost structures (unit
variable costs plus avoidable fixed costs) for the three machines are shown below. The selling price is
unaffected by the machine used.
Single purpose machine ₹ 0.60 + ₹ 20,000 Semi-automatic machine ₹ 0.40 + ₹ 50,000 Automatic machine ₹
0.20 + ₹ 120,000
The demand for units of the new product is described by the following probability distribution:
Demand Probability
200,000 0.4
300,000 0.3
400,000 0.2
500,000 0.1
Calculate expected demand. Calculate the expected costs of using the semi-automatic machine. Which
machine should be selected?
Que 25 (SM EX Q6 – 585)

Your client, Alpha Ltd., wants your advice on which of two alternatives he should choose. One alternative is to
sell an investment now for ₹ 10,000. Another alternative is to hold the investment three days; after which he
can sell it for a certain selling price based on the following probabilities:
Selling Price (₹) Probability
5,000 0.4
8,000 0.2
12,000 0.3
30,000 0.1
Would you recommend selling the investment now or hold the investment for three days?
Que 26 (SM EX Q7 – 585)

The TTC Company is considering hiring several new employees to handle an overload from a new contract. If

the new people are not hired, there will be delays in the contract work. The following payoff matrix has been
prepared for analysing whether new people are needed:
Particulars [Hire New] [Do Not Hire]
New People People
Retain new customers ₹100,000 ₹75,000
Lose new customers ₹25,000 ₹50,000
Based on past experience, the company expects to retain 75% of the new customers with no new hires
Calculate the expected profit for the “no hire” decision
Que 27 (SM EX Q 8 – 586)

Cement Co is a company specialising in the manufacture of cement, a product used in the building industry.
The company has found that when weather conditions are good, the demand for cement increases since more
building work is able to take place. Cement Co is now trying to work out the level of cement production for
the coming year in order to maximise profits. The company has received the following estimates about the
probable weather conditions and corresponding demand levels for the coming year:
Weather Probability Demand
Good 25% 350,000 bags
Average 45% 280,000 bags
Poor 30% 200,000 bags
Each bag of cement sells for ₹ 9 and costs ₹ 4 to make. If cement is unsold at the end of the year, it has to be
disposed of at a cost of ₹ 0·50 per bag. Cement Co has decided to produce at one of the three levels of
production to match forecast demand. It now has to decide which level of cement production to select.
Construct a pay-off table to show all the possible profit outcomes.
Que 28 (Unsolved case 1 – 586)

Suppose you are the Manager Cost of your company and you have to choose between mutually exclusive
options A and B. The probable outcomes of each option are as follows.
Option A Option B
Probability Profit Probability Profit
0.8 5,000 0.1 (2,000)
0.2 6,000 0.2 5,000
Explain how you can arrive at a decision, for selecting either Option A or Option B?

Decision Theory

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Decision Theory

Uploaded by

Copyright:

Available Formats

CMA Inter – P12 – Management Accounting – Decision Theory

Identify the nature of decision

Gather relevant information from Internal & external Sources

Consider the evidences

Review of the decision

Decision making in Certainty

Table: Decision Matrix

Ai Oil Oi2 ----- Oij ----- Oin

Am Oml Om2 ----- Omj ----- Omn

Pay off Matrix (under condition of certainty)

Decision making Under Risk

Subjective & Objective Probabilities

Probability in Different Events

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.3

Methods Of Assigning Probable Values

Expected Value / Mean /Average Value (or Expected Return)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.5

Decision making Under Uncertainity

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.6

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.7

4. Essay Type Questions:

Practical Questions & Case Studies

Que 2 (SM Solved case 2 – 542)

Que 3 (SM Solved case 3 – 544)

Que 4 (Illustartion 1 – 547)

Que 5 (Illustartion 2 – 547)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.12

Que 6 (Illustartion 3 – 548)

Que 7 (Illustartion 4 – 551)

Que 8 (Illustartion 5 – 552)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.13

Que 9 (Illustartion 6 – 553)

Que 10 (Illustartion 7 – 554)

Que 11 (Illustartion 8 – 558)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.14

Que 13 (Illustartion 10 – 563)

Que 14 (Illustartion 11 – 564)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.15

Que 15 (Illustartion 12 – 566)

Que 16 (Illustartion 13 – 567)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.16

Que 17 (Illustartion 14 – 568)

Que 18 (Illustartion 15 – 570)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.17

Que 19 (Illustartion 16 – 571)

Profits of ₹ 4,00,000 0.05 20,000

Que 20 (SM EX Q 1 – 583)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.18

Selling price of ₹ 8.20:

Que 21 (SM EX Q 2 – 584)

Que 22 (SM EX Q 3 – 584)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.19

Que 23 (SM EX Q 4 – 584)

Que 24 (SM EX Q5 – 585)

Que 25 (SM EX Q6 – 585)

Que 26 (SM EX Q7 – 585)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.20

Que 27 (SM EX Q 8 – 586)

Que 28 (Unsolved case 1 – 586)

CA ADITYA SHARMA WHATSAPP No: 8767878282 Page No. 7.21

You might also like